Human activity recognition based on transformed accelerometer data from a mobile phone

Mobile phones are equipped with a rich set of sensors, such as accelerometers, magnetometers, gyroscopes, photometers, orientation sensors, and gravity sensors. These sensors can be used for human activity recognition in the ubiquitous computing domain. Most of reported studies consider acceleration signals that are collected from a known fixed device location and orientation. This paper describes how more accurate results of basic activity recognition can be achieved with transformed accelerometer data. Based on the rotation matrix (Euler Angle Conversion) derived from the orientation angles of gyroscopes and orientation sensors, we transform input signals into a reference coordinate system. The advantage of the transformation is that it allows activity classification and recognition to be carried out independent of the orientation of sensors. We consider five user activities: staying, walking, running, ascending stairs, and descending stairs, with a phone being placed in the subject's hand, or in pants pocket, or in a handbag. The results show that an overall orientation independent accuracy of 84.77% is achieved, which is a improvement of 17.26% over those classifications without input transformation. Copyright © 2014 John Wiley & Sons, Ltd.     

Compressed sensing method for human activity recognition using tri-axis accelerometer on mobile phone

The diversity in the phone placements of different mobile users' dailylife increases the difficulty of recognizing human activities by using mobile phone accelerometer data. To solve this problem, a compressed sensing method to recognize human activities that is based on compressed sensing theory and utilizes both raw mobile phone accelerometer data and phone placement information is proposed. First, an over-complete dictionary matrix is constructed using sufficient raw tri-axis acceleration data labeled with phone placement information. Then, the sparse coefficient is evaluated for the samples that need to be tested by resolving L1 minimization. Finally, residual values are calculated and the minimum value is selected as the indicator to obtain the recognition results. Experimental results show that this method can achieve a recognition accuracy reaching 89.86%, which is higher than that of a recognition method that does not adopt the phone placement information for the recognition process. The recognition accuracy of the proposed method is effective and satisfactory.     

基于FMCW雷达的多通道特征融合人体动作识别方法

针对采用单一特征进行人体动作识别准确率不高的问题,提出了一种基于调频连续波(Frequency Modulated Continuous Wave, FMCW)雷达的多通道特征融合人体动作识别方法。通过对FMCW雷达回波数据进行预处理,得到人体动作的距离参数与多普勒参数,构建出距离-时间特征谱图和多普勒-时间特征谱图数据集。为了进行人体动作特征的充分提取与精确识别,改进了单通道输入的传统卷积神经网络结构,把部分残差连接结构和跨阶段部分连接结构进行了优化应用至雷达人体动作识别领域,设计出端到端的CSP-FCNN(Cross Stage Partial-Fusion Convolutional Neural Network)多通道融合卷积神经网络。采用公开数据集进行实验,结果表明所提方法有效解决了单一特征动作识别信息量欠缺以及网络提取特征不充分的问题,识别准确率较单一特征识别方法提高了5%以上。     

Novel approaches to signal transmission based on chaotic signalsand artificial neural networks

A novel chaotic-based coding/decoding strategy that exploits radial basis function (RBF) artificial neural networks (ANNs) in a dynamic feedback (DF) configuration is reported. The ANNs are used as pseudochaotic carrier generators and as estimators for the received signal. The dynamics approximated were those of the logistic map (LM). This approach is compared with established methods that employ inversion, dynamic feedback, and least mean square (LMS) and recursive least squares (RLS) estimation. Our RBF-ANN-DF approach is shown to outperform these methods in terms of the recovered signal SNR at various channel SNRs with a speech information signal used as an example. In particular, the RBF-ANN-DF method is shown to outperform DF approaches by about 33 dB at all channel SNRs. Moreover, the proposed RBF-ANN-DF approach offers a recovered signal SNR improvement between about 15.1 and 27.4 dB for channel SNRs between 10 and 50 dB as compared to an LMS-based chaotic receiver. As a by-product, we have also shown that, for the logistic map, LMS- and RLS-based chaotic receivers are equivalent and, hence, the use of LMS-based receivers can result in implementation savings     

Speech emotion recognition approaches in human computer interaction

Speech Emotion Recognition (SER) represents one of the emerging fields in human-computer interaction. Quality of the human-computer interface that mimics human speech emotions relies heavily on the types of features used and also on the classifier employed for recognition. The main purpose of this paper is to present a wide range of features employed for speech emotion recognition and the acoustic characteristics of those features. Also in this paper, we analyze the performance in terms of some important parameters such as: precision, recall, F-measure and recognition rate of the features using two of the commonly used emotional speech databases namely Berlin emotional database and Danish emotional database. Emotional speech recognition is being applied in modern human-computer interfaces and the overview of 10 interesting applications is also presented in this paper to illustrate the importance of this technique.     

基于Kinect的实时人体姿势识别

Kinect的实时骨骼跟踪技术获取身体关节点的三维位置信息,为进行人体姿势识别提供了丰富的信息,拟在三维关节点位置信息的基础上,建立一种实时的人体姿势识别系统。选择关节角度作为姿势特征,结合逻辑回归（logistic regression,LR）分类算法对54种姿势进行识别研究。实验结果表明,该姿势识别系统可以准确实时地识别人体姿势。     

基于谐振原理的硅微机械加速度计

基于力学振动原理 ,导出敏感梁类谐振振动的微分方程 ,给出了振梁型加速度计的设计原理。指出了加速度计谐振梁频率的相对变化量与梁的厚度无关 ;为避免输出非线性频率信号 ,频率的相对变化率和激励振动的振幅都不宜太大     

基于谐振原理的硅微机械加速度计

基于力学振动原理，导出敏感梁类谐振振动的微分方程，给出了振梁型加速度计的设计原理。指出了加速度计谐振梁频率的相对变化量与梁的厚度无关；为避免输出非线性频率信号，频率的相对变化率和激励振动的振幅都不宜太大。     

基于双悬臂梁结构的光纤加速度传感器

为消除悬臂梁结构加速度传感器由于光纤表面粘贴产生的啁啾现象,增强横向抗干扰能力,提高共振频率,提出了一种基于双悬臂梁结构的光纤加速度传感器。给出了理论分析结果,建立了有限元模型,得到了加速度灵敏度表达式,并且探讨了在共振频率不变的情况下提高加速度灵敏度的方法。实验结果表明,该传感器在6～50 Hz内频响平坦,加速度灵敏度为14pm/g,抗横向干扰能力达20dB,与理论计算较好地吻合。     

新颖的差值扩展可逆数据隐藏算法

提出一种变换方向自适应的差值扩展可逆数据隐藏算法(ACD),ACD通过扩展像素对的差值嵌入数据。像素对中一为参照像素,另一为变换像素,ACD根据像素对所处区域类型的估测,自适应选择变换像素,暗区选大值像素,亮区选小值像素,否则选默认方向像素。理论分析及实验结果表明,ACD解决了预测误差扩展可逆数据隐藏算法(PEE)在暗或亮载体时灰度溢出急剧增加的问题,与采用现有灰度溢出解决方案的PEE相比,改善了载体普适性,性能更稳定。     

一种基于boosting特征选择的调制方式识别算法

针对统计调制模式识别方法中特征值提取和分类器设计两个步骤分开研究的现状,将Boosting特征选择和多层前馈神经网络算法结合研究,设计了一种改进算法,给出算法的具体步骤.使用常用特征值进行仿真实验,结果表明这种改进算法在信噪比在0 dB以上达100％的识别率.相比其他的智能分类算法,信噪比在-6 dB以下时改进算法的识别率有明显提高,因此可以较好地适用于认知无线电这种对识别准确率要求高的场景中.同时对其他分类识别的应用场景也有一定的参考价值.     

一种基于改进DTW算法的动态手势识别方法

结合Kinect传感器提出了一种基于改进的DTW算法的动态手势识别方法。首先,通过SDK对Kinect传感器获得的深度信息进行分析,获得人体骨骼点3D位置,选取其中4个点作为手部运动特征;然后,用加权距离和全局路径限制的方法对传统的DTW算法进行改进;最后,用改进的DTW算法进行模板训练和实现动态手势的识别。实验表明：该方法能很好地实现动态手势的识别,实时性好,在背景干扰和光照方面有较强的鲁棒性,较传统的DTW算法在识别速度和识别正确率方面有所提高。     

Cross-view gait recognition based on human walking trajectory

We propose in this paper a novel cross-view gait recognition method based on projection of gravity center trajectory (GCT). We project the coefficients of 3-D GCT in reality to different view planes to complete view variation. Firstly, we estimate the real GCT curve in 3-D space under different views by statistics of limb parameters. Then, we get the view transformation matrix based on the projection principle between curve and plane, and estimate the view of a silhouette sequence by this matrix to complete view variance of gait features. We calculate the body part trajectory on silhouette sequence to improve recognition accuracy by using correlation strength as similarity measure. Lastly, we take nested match method to calculate the final matching score of two kinds of features. Experimental results on the widely used CASIA-B gait database demonstrate the effectiveness and practicability of the proposed method.     

基于微电铸的非硅MEMS加速度传感器

简单介绍了Silicon Design公司开发的非硅MEMS传感器的设计、工艺、输出信号的处理技术.通过巧妙设计和使用铸Ni技术成功地改善了梁的扭摆特性.实测结果表明,10 g产品的输出交流噪声有效值和漂移被分别控制在0.4 mV和4 mV;50 g产品虽然漂移偏大,但其线性系数K2还是达到了10-3～10-4的水准.     

基于Hopkinson杆的高g值加速度计的标定

介绍了基于Hopkinson杆技术的激光光栅干涉法冲击加速度计的绝对校准方法。采用激光干涉仪对激励信号进行测量,实现对高g值加速度计的标定。给出了高g值加速度传感器的灵敏度标定公式,并通过比较说明了两种公式的优缺点。实验结果表明,本文中的标定方法可满足标定的精度要求。     

A triaxial accelerometer and portable data processing unit for theassessment of daily physical activity

The present study describes the development of a triaxial accelerometer (TA) and a portable data processing unit for the assessment of daily physical activity. The TA is composed of three orthogonally mounted uniaxial piezoresistive accelerometers and can be used to register accelerations covering the amplitude and frequency ranges of human body acceleration. Interinstrument and test-retest experiments showed that the offset and the sensitivity of the TA were equal for each measurement direction and remained constant on two measurement days. Transverse sensitivity was significantly different for each measurement direction, but did not influence accelerometer output (<3% of the sensitivity along the main axis). The data unit enables the on-line processing of accelerometer output to a reliable estimator of physical activity over eight-day periods. Preliminary evaluation of the system in 13 male subjects during standardized activities in the laboratory demonstrated a significant relationship between accelerometer output and energy expenditure due to physical activity, the standard reference for physical activity (r=0.89). Shortcomings of the system are its low sensitivity to sedentary activities and the inability to register static exercise. The validity of the system for the assessment of normal daily physical activity and specific activities outside the laboratory should be studied in free-living subjects     

一种新结构介观压光型微加速度计

对镜像异质三周期光子晶体的研究理论表明,在实际应用范围内,透射率与光子晶体所受的轴向应力呈简单的线性关系。据此,设计一种能实现微梁直拉直压的加速度计,微梁很小很敏感,处于轴向直拉直压位置时,能极大提高结构的灵敏度和自由振动频率。以镜像异质三光子晶体替代以往的压敏电阻,只需检测其透射率,即可得出加速度大小。最后结果表明:当透射光强改变1时,该结构可以感知小于0.4 mgn的加速度的变化,测量量程可达3.2 gn。     

基于数据融合与迁移学习的学生表情识别研究

学生表情逐渐成为感知学生状态的重要途径,因此准确的识别学生表情因具有重要价值而受到广泛的关注.本文针对学生表情识别这一问题,提出基于数据融合与迁移学习的识别模型,该模型融合3个数据集,以解决学生表情数据缺乏与多样性问题,同时引入迁移学习来提升预测精度.在数据集及实际学生表情图像上的实验结果表明,本文提出的模型可以准确识别学生表情,提升了预测精度.     

基于数据增强算法和CNN-LSTM的高精确度手势识别

近年来,基于雷达的手势识别技术在工业和生活中得到了广泛应用,但愈加复杂的应用场景对手势识别算法的准确率和鲁棒性提出了更高要求。对此,设计了一种基于毫米波雷达的高精确度手势识别算法。通过对已有分类算法的研究对比,构建了一种用于手势识别的卷积神经网络-长短期记忆网络(CNN-LSTM)深度学习算法模型;同时,运用布莱克曼窗抑制手势信号处理中的频谱泄露问题,并联合运用小波阈值和动态补零算法实现高效杂波抑制和数据增强。实测结果表明,设计的手势识别算法正确分类率达到97.29%,在不同的距离和角度情况下也可以保持较好的识别准确率,具有良好的鲁棒性。